PredictorRunParams¶

tiatoolbox . models . engine . patch_predictor . PredictorRunParams

class PredictorRunParams[source]¶

Parameters for configuring the PatchPredictor.run() method.

This class extends EngineABCRunParams with additional parameters specific to patch-level prediction workflows.

auto_get_mask¶

Whether to automatically generate segmentation masks using wsireader.tissue_mask() during processing.

batch_size¶

Number of image patches to feed to the model in a forward pass.

class_dict¶

Optional dictionary mapping classification outputs to class names.

device¶

Device to run the model on (e.g., “cpu”, “cuda”).

labels¶

Optional labels for input images. Only a single label per image is supported.

memory_threshold¶

Memory usage threshold (in percentage) to trigger caching behavior.

num_workers¶

Number of workers used in DataLoader.

output_file¶

Output file name for saving results (e.g., .zarr or .db).

return_labels¶

Whether to return labels with predictions.

return_probabilities¶

Whether to return per-class probabilities in the output. If False, only predicted labels are returned.

scale_factor¶

Scale factor for converting annotations to baseline resolution. Typically model_mpp / slide_mpp.

stride_shape¶

Stride used during WSI processing. Defaults to patch_input_shape.

verbose¶

Whether to output logging information.

Methods

Attributes